Spinoff is NASA's annual publication featuring successfully commercialized NASA technology. This commercialization has contributed to the development of products and services in the fields of health and medicine, consumer goods, transportation, public safety, computer technology, and environmental resources.

Once you've designed a robot that can autonomously explore planetary terrain, putting the same technology in cars, toys, and drones seems almost easy. That's why conducting NASA-funded research on deep-space computing was a natural fit for Boston-based startup Neurala. The company's core technology is an artificial intelligence (AI) “brain” — neural network software modeled on the human brain that can interact with and learn from its environment using ordinary cameras and sensors. The Neurala Brain can process its surroundings locally, so it doesn't require a cloud-based supercomputer like other AI systems. That's where the NASA research was especially crucial.

To put a self-learning robot on Mars, for instance, where communication with Earth can be delayed by as much as 25 minutes, “you need to rely only on the compute power that you have onboard,” explained Massimiliano Versace, who founded Neurala with colleagues at Boston University. “You cannot ping a server. You don't have GPS. You don't want to send to Mars something that can break or fail, or needs a lot of communication and exchanges with Earth.”

A system that can work under these demanding conditions has far fewer hurdles on Earth. The idea for Neurala came in 2005, when Versace and his colleagues realized that major developments in the latest graphics processing units weren't just good for video games — they also had game-changing potential for artificial intelligence.

“The intuition we had back then was: what if each pixel that the graphic processor processes is treated like a neuron?" Versace recalled. The colleagues started using graphics cards to develop programs that operated more like brains that can slowly compute a large amount of information in parallel versus a traditional central processing unit that can process many small pieces of information very fast, but serially.

This screenshot shows a self-driving car's view when powered by Neurala's software. The vehicle can automatically identify pedestrians, cars, cyclists, trucks, and more on a Boston street in real time.

A signal that this research could have more than a theoretical impact came in 2009, when the team started working on the Defense Advanced Research Projects Agency (DARPA) SyNAPSE Project that aimed to develop low-power computers inspired by biological neural systems — specifically, brains. NASA got wind of the work in 2010, when Versace wrote about the DARPA research. Mark Motter, an engineer at NASA's Langley Research Center, read the article and saw broad potential for the brain-inspired system. He reached out to the Neurala founders and eventually became the technical representative on the company's Small Business Technology Transfer (STTR) contracts with Langley.

“The first phase of the award was focused on showing how a rover on Mars would learn to navigate within an unsupervised neuromorphic computing paradigm and find its way in an unfamiliar environment,” Motter said. At the time, exploring planetary surfaces still required human control and power-hungry sensors. There was a sense that AI was the way forward, but it was still unproven.

In 2011, Neurala completed its STTR Phase I research before winning a Phase II contract, for which the company developed another key to what would soon become its commercial offerings: visual processors based on passive sensors to enable robots to identify and interact with objects and learn new terrain. Motter, whose Ph.D. work involved unsupervised learning and could be applied to drones, took interest in Neurala's research since the visual processors had clear potential benefits on Earth.

Following the NASA work, Neurala was able in 2014 to raise $750,000 in private capital. The company then applied for and was awarded an additional $250,000 from NASA.

Neurala created several iOS and Android apps for consumer robots and drones. The company is also licensing the technology to consumer drone manufacturers. The products have helped the company reach its real market: designers and manufacturers. By the time Neurala announced in 2016 that it had raised $14 million, it already had contracts with several drone companies, industrial robot manufacturers, and a major automaker looking toward self-driving cars, where the ability to make calculations locally is vital.

“If you're a drone flying 50 miles an hour, by the time you send video to the cloud where a program identifies a bird in your path and sends back information to steer, you've already hit the bird,” Versace said. “You want to be able to compute quickly on the device for safety reasons.”

The company's main product, its Brains for Bots software development kit, enables app developers to incorporate the Neurala Brain into programs created for a variety of computing platforms used in drones, self-driving cars, industrial robots, smart cameras, toys, mobile phones, and computers. The software can learn to identify, find, and track objects. Later iterations of the software will incorporate navigation and advanced collision avoidance. Recent projects for Neurala include a partnership with Motorola to incorporate facial recognition into cameras worn by police.

Visit here .

Tech Briefs Magazine

This article first appeared in the September, 2018 issue of Tech Briefs Magazine.

Read more articles from this issue here.

Read more articles from the archives here.